Point cloud segmentation for unstructured regions is challenging. Especially, the diversity and complexity of the terrains in surface mine make point cloud segmentation more difficult, which brings potential risks for autonomous driving. To solve this problem, a Variance and Slope ratio based Segmentation method, named VSSeg was proposed. The proposed VSSeg method takes advantage of the different distributions of scatter diagrams projected in the height direction to obtain the variance-based discriminant slope characteristics. And it uses the slope changes at critical points of the ground and the unstructured regions to achieve slope-ratio-based segmentation. Experiments were conducted on the mining datasets with annotation, and the results showed the effectiveness and robustness of our proposed VSSeg method. Especially, for dumping berm segmentation, the accuracy reached 95% on average with a real-time speed.